ask-dont-assume

ask-dont-assume is a skill for Claude Code, Codex from buildmoonshot/skillpacks. It costs 61 tokens per session (388 once invoked), scanned A, original, MIT.

A workflow rule for handling requests that have more than one reasonable interpretation or lack important details. It tells the agent to ask a focused question or state its assumption before proceeding.

In plain words
What is it for?
Use it before implementing unclear requests, especially when the choice affects files, formats, behavior, security, data, or other high-impact outcomes.
Why use it?
It prevents code from being built around a hidden guess and makes decisions easy to correct when the request is ambiguous.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before implementing unclear requests, especially when the choice affects files, formats, behavior, security, data, or other high-impact outcomes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/buildmoonshot/skillpacks/ask-dont-assume
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add buildmoonshot/skillpacks --skill ask-dont-assume
Clone the repo
git clone --depth 1 https://github.com/buildmoonshot/skillpacks

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ask-dont-assume

README.md
[![agentmods](https://agentmods.dev/badge/skills/buildmoonshot/skillpacks/ask-dont-assume.svg)](https://agentmods.dev/skills/buildmoonshot/skillpacks/ask-dont-assume)
Your own site
<a href="https://agentmods.dev/skills/buildmoonshot/skillpacks/ask-dont-assume"><img src="https://agentmods.dev/badge/skills/buildmoonshot/skillpacks/ask-dont-assume.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 388 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.00388
Opus 5 $0.00030 $0.00194
Sonnet 5 $0.00012 $0.00078
Haiku 4.5 $0.00006 $0.00039

Measured 8d ago against content hash f7cc92f21639, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ask-dont-assume scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/engineering/beginner/ask-dont-assume/SKILL.md · 27 lines

What it actually says

Ask, Don't Assume

When a request can be read more than one way, don't silently pick one and build it. Surface the fork first.

What to do

  1. Spot the ambiguity. Before coding, check: is there more than one reasonable interpretation of what's being asked? Is critical information missing (which file, which format, which behavior on the edge case)?

  2. Then choose how to proceed:

    • High stakes or genuinely unclear → ask a short, specific question. Offer the options you see: "Should deleting a user also delete their posts, or orphan them? I'd default to orphaning."
    • Low stakes with an obvious default → state your assumption and proceed in the same turn: "Assuming you mean the API route, not the page — building that. Say the word if it's the page."
  3. Make assumptions visible, always. Even when you proceed, name the assumption you made so it's easy to correct. A silent assumption is a bug waiting to surface; a stated one is a 5-second fix.

Don't over-correct

This isn't "ask about everything." Endless clarifying questions are their own failure. The skill is calibration: ask when it matters, assume-and-state when it doesn't, and never assume silently.

Why this matters

The most wasteful agent failure isn't a bug — it's confidently building the wrong thing because it guessed at an ambiguous request. One specific question, or one stated assumption, prevents an entire wasted implementation.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 27 lines · 61 tokens per session scan A f7cc92f21639

Subscribe to this mod's changes

ask-dont-assume is a skill published in the GitHub repository buildmoonshot/skillpacks (2 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 388 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

writers-pattern

Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform. Each writer exports a function that accepts a config interface, creates directories (rules/, skills/, mcp configs), writes files with proper formatting and frontmatter, and returns string[] of…

caliber-ai-org/ai-setup · 111 tokens

caliber-testing

Writes Vitest tests following project patterns: tests/ directories, vi.mock() for module mocking with vi.hoisted() for test-time factories, global LLM mock from src/test/setup.ts, environment variable save/restore in beforeEach/afterEach, vi.clearAllMocks() lifecycle, and test file organization. Use when user says…

caliber-ai-org/ai-setup · 113 tokens

llm-provider

Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods. Integrates with provider factory in src/llm/index.ts, config detection in src/llm/config.ts, and error handling via tracking and recovery. Use when adding a new model backend, integrating a third-party LLM API, or extending…

caliber-ai-org/ai-setup · 100 tokens

scoring-checks

Add a new deterministic scoring check in src/scoring/checks/ that evaluates config quality. Follows the Check[] return pattern, uses point constants from src/scoring/constants.ts, and integrates via filterChecksForTarget() in src/scoring/index.ts. Use when user says 'add scoring check', 'new check', 'modify scoring…

caliber-ai-org/ai-setup · 95 tokens

adding-a-command

Creates a new CLI command following the Commander.js pattern in src/commands/. Handles command registration in src/cli.ts, telemetry tracking via tracked() wrapper, and option parsing. Use when user says add command, new CLI command, create subcommand, or adds files to src/commands/. Do NOT use for modifying existing…

caliber-ai-org/ai-setup · 76 tokens

setup-caliber

Sets up Caliber for automatic AI agent context sync. Installs pre-commit hooks so CLAUDE.md, Cursor rules, and Copilot instructions update automatically on every commit. Use when Caliber hooks are not yet installed or when the user asks about keeping agent configs in sync.

caliber-ai-org/ai-setup · 61 tokens